Opens a shiny app for the roulette elicitation method. The user clicks in the grid to allocate 'probs' to 'bins'. The elicited probability inside each bin is the proportion of probs in each bin. This will fit a distribution to the ratio R of the 'largest' (97.5th percentile) to 'smallest' (2.5th percentile) treatment effect. A distribution for the variance effects variance parameter is inferred from the distribution of R, assuming that the random effects are normally distributed.
elicitHeterogen(
lower = 1,
upper = 10,
gridheight = 10,
nbins = 9,
scale.free = TRUE,
sigma = 1
)BUGS code for incorporating the prior within a BUGS model. Additionally, a list with outputs
table of bins, with number of probs allocated to each bin.
parameters of the fitted gamma distribution.
parameters of the fitted lognormal distribution.
sum of squares of elicited - fitted probabilities for each distribution.
the distribution with the lowest sum of squares.
The lower limit on the x-axis of the roulette grid.
The upper limit on the x-axis of the roulette grid.
The maximum number of probs that can be allocated to a single bin.
The number of equally sized bins drawn between lower and
upper.
Logical. Default is TRUE for a scale free treatment effect,
such as an odds ratio, hazard ratio or relative risk. Set to FALSE for a treatment effect
that is scale dependent, or is on the probit scale. An approximation to the treatment effect
on the logit scale will be used (assuming a dichotomised response).
Individual observation standard deviation, required if scale.free is
FALSE.
Jeremy Oakley <j.oakley@sheffield.ac.uk>
if (FALSE) {
elicitHeterogen()
}
Run the code above in your browser using DataLab